What harness do you use Gemini in?

agy cli. It’s been rock solid.

Interesting product. I know others building in this space. How are things going with existing customers? And how are you measuring deltas vs standard agentic processes? Are you using RAG under the hood?

Thanks for asking! Existing customers use Hyper consistently to power agents for email drafting, managing inbound, generating marketing materials, improving debugging workflows, and as a "backbone" for long-running parallel coding agents. Having relevant, narrow context at all times greatly improves performance.

Right now our measurements are primarily subjective; we have several customers tell us "Hyper let my agent draft outbound/do market research/run experiments overnight with no intervention or follow-ups, when I would have to constantly babysit it in the past." We have also run Hyper's algorithms on common benchmarks versus more traditional methods. I don't want to claim numbers before we've verified them, but Hyper performs significantly better.

We do not use RAG in the traditional sense (semantic similarity across chunked source documents). We use hybrid retrieval methods to fetch relevant information across our carefully designed knowledge graph, and then have shallow agents consolidate retrieved information into a format that the invoking agent can understand.

Are there others in this space doing a good job? Curious about what else is tackling this.

Also commenting to say I really enjoyed it.

I’m trying to build SmallDocs, a new markdown first browser based document format (mainly for ease of use by agents): https://sdocs.dev

More info on a ShowHN here: https://news.ycombinator.com/item?id=47777633

I’ve been building something somewhat adjacent to this. It’s https://sdocs.dev. It’s as 100% private browser based Markdown renderer

It's nice to see people building things, but honestly I found the demo video a bit disappointing. A bit too slow, a bit too choppy, a bit hand wavy. It didn't make me grasp why I needed this in my life.

I like it. I am building something very agent-use focused (https://sdocs.dev) and I’ve been thinking of introducing a /agent-evaluation page, which an agent can curl to then discuss with their user if SmallDocs is right for them. I really like the agent action to email flow. I’m introducing user accounts + subscriptions soon and think I’ll use that.

And now we see the beginning of how even local LLMs will be turned against their users -- by persuading agents to advertise to them.

I don't think that's what you're intending here, but it's the next logical step. Agents are on the Internet, and they represent an opportunity to reach their humans.

Thanks very much. I found that a very thoughtful reply

This is exactly my view and exactly what I’m building at https://sdocs.dev.

It’s Word if it were for cli based agents. It’s cli-first, markdown first, and you rarely if ever create the docs. Instead you tell your agent, “research X and give it to me in a sdoc”, or “sdoc this bug report so I can share it with Andy”.

It was discussed on a Show HN here: https://news.ycombinator.com/item?id=47777633

Nice, this feels very aligned with the direction I was trying to describe.

I’ll take a closer look at sdocs. Thanks for sharing!